Mean dimension of radial basis functions
From MaRDI portal
Abstract: We show that generalized multiquadric radial basis functions (RBFs) on have a mean dimension that is as with an explicit bound for the implied constant, under moment conditions on their inputs. Under weaker moment conditions the mean dimension still approaches . As a consequence, these RBFs become essentially additive as their dimension increases. Gaussian RBFs by contrast can attain any mean dimension between 1 and d. We also find that a test integrand due to Keister that has been influential in quasi-Monte Carlo theory has a mean dimension that oscillates between approximately 1 and approximately 2 as the nominal dimension increases.
Recommendations
- Α Study on Radial Basis Function and Quasi-Monte Carlo Methods
- The near-equivalence of five species of spectrally-accurate radial basis functions (RBFs): Asymptotic approximations to the RBF cardinal functions on a uniform, unbounded grid
- scientific article; zbMATH DE number 778115
- scientific article; zbMATH DE number 1795892
Cited in
(1)
This page was built for publication: Mean dimension of radial basis functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6426969)